Student theses

Below are our current open bachelor and master thesis topics. If you are interested in learning more about a topic, please contact the person assigned to that topic or visit us at our offices.

You can also contact our team members for more currently open theses topics or if you want to suggest a topic yourself!

Open Bachelor Thesis Topics

Student-Teacher vs. Teacher-Student Learning: Wer sollte schneller lernen für besseren gemeinsamen Erfolg?

Kontakt: Adrian Redder
Details zur Bachelorarbeit finden Sie hier.

Referenz Gouverneur für Modelfreie Regelungen

Kontakt: Adrian Redder

Details zur Bachelorarbeit finden Sie hier.

Parameteridentifikation und Sensitivitätsanalyse für das rotierende inverse Pendel

Kontakt: Adrian Redder
Details folgen..

Open Master Thesis Topics

Active SLAM for aerial robots in dense environments

Contact: Julio Betancourt
Please find details about the master thesis here.

Safe control of aerial robots based on robust control barrier functions for wind turbine inspection

Contact: Julio Betancourt
Please find details about the master thesis here.

Data-driven model predictive control of a flapping-wing system

Contact: Julio Betancourt
Please find details about the master thesis here.

Nonlinear control for a tilting quadrotor

Contact: Julio Betancourt
Please find details about the master thesis here.

Hierarchical Optimization and Deep Multi-Agent Reinforcement Learning for Coverage Control with unknown Points of Interest

Contact: Adrian Redder
Please find details about the master thesis here.

Metrics for assessing data selection for Visual Odometry training

Master’s thesis, in a collaboration with Aarhus University, Denmark
Deep learning has led to the development of end-to-end methods for visual odometry (VO), setting up a new paradigm for this family of algorithms. The higher-level representation of the environment that deep learning introduces allows it to generate estimates under challenging imaging conditions that make traditional algorithms fail. However, their performance is conditioned by the selected training environment. This limitation has been mainly addressed by feeding more and more varied data to the network. The present work aims to assess the information in the datasets from which the algorithm is learning. For that, a set of metrics to deploy on the target datasets will be developed. The aim of these metrics is twofold: firstly, to assess the quality and variability of the data available, and secondly, to establish a criterion for the data splitting in learning-based VO.
Contact: Erdal Kayacan